CN114610559A - Equipment operation environment evaluation method, judgment model training method and electronic equipment - Google Patents
Equipment operation environment evaluation method, judgment model training method and electronic equipment Download PDFInfo
- Publication number
- CN114610559A CN114610559A CN202011406910.1A CN202011406910A CN114610559A CN 114610559 A CN114610559 A CN 114610559A CN 202011406910 A CN202011406910 A CN 202011406910A CN 114610559 A CN114610559 A CN 114610559A
- Authority
- CN
- China
- Prior art keywords
- equipment
- training
- sample
- evaluated
- temperature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012549 training Methods 0.000 title claims abstract description 119
- 238000000034 method Methods 0.000 title claims abstract description 82
- 238000011156 evaluation Methods 0.000 title claims abstract description 81
- 230000007613 environmental effect Effects 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims description 16
- 238000013139 quantization Methods 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 5
- 238000011002 quantification Methods 0.000 claims description 2
- 238000013021 overheating Methods 0.000 description 20
- 230000000875 corresponding effect Effects 0.000 description 18
- 238000004364 calculation method Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000017525 heat dissipation Effects 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000020169 heat generation Effects 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3058—Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Evolutionary Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Quality & Reliability (AREA)
- Medical Informatics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides an equipment operating environment evaluation method, a judgment model training method and electronic equipment, wherein the equipment operating environment evaluation method comprises the following steps: acquiring environmental parameters of an operating environment to be evaluated; acquiring equipment parameters and device parameters of the equipment sample to be evaluated in the running environment to be evaluated; determining a decision scene according to the environment parameters, the equipment parameters and a pre-trained decision model, and determining an equipment evaluation result of the equipment sample to be evaluated in the decision scene according to the device parameters of the equipment sample to be evaluated; and determining the operation environment evaluation result of the operation environment to be evaluated according to the equipment evaluation result. According to the scheme provided by the embodiment of the invention, the evaluation result of the equipment operation environment can be obtained in the normal operation state of the equipment, so that an information basis is provided for predicting the influence of the operation environment on the equipment temperature.
Description
Technical Field
The present invention relates to, but not limited to, the field of data processing, and in particular, to an apparatus operating environment evaluation method, a decision model training method, and an electronic apparatus.
Background
The electronic communication equipment can generate heat in the operation process, and the electronic communication equipment can cause certain influence on the working performance and the service life of the equipment and even damage the equipment when operated in an overheat state. For a device installed at a fixed position, the heat dissipation performance depends not only on the heat dissipation manner and materials of the device itself, but also on the specific operating environment, for example, when the device is in an enclosed or close-to-heat operating environment, the heat dissipation effect is usually poor, and the device is easily overheated. Therefore, in the process of modifying or troubleshooting the operating environment of the equipment, it is necessary to analyze every factor that may cause the temperature of the equipment to be overheated.
In order to evaluate the influence of the operating environment on the temperature of the equipment, the temperature of the operating environment is mainly detected by a temperature detection device at present, so that real-time data or a change curve of the environmental temperature is obtained and compared with a numerical value of the temperature of the equipment. However, the temperature value of the operating environment of the device in the overheat state must be obtained, and the influence of the operating environment on the temperature of the device cannot be evaluated when the device is in normal operation.
Disclosure of Invention
The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.
The embodiment of the invention provides an equipment operating environment evaluation method, a judgment model training method and electronic equipment, which can finish evaluation of an operating environment in the normal operating process of the equipment.
In a first aspect, an embodiment of the present invention provides an apparatus operating environment assessment method, including:
acquiring environmental parameters of an operating environment to be evaluated;
acquiring equipment parameters and device parameters of the equipment sample to be evaluated in the operating environment to be evaluated;
determining a decision scene according to the environment parameters, the equipment parameters and a pre-trained decision model, and determining an equipment evaluation result of the equipment sample to be evaluated in the decision scene according to the device parameters of the equipment sample to be evaluated;
and determining the operation environment evaluation result of the operation environment to be evaluated according to the equipment evaluation result.
In a second aspect, an embodiment of the present invention further provides a decision model training method, including:
determining a training sample set, wherein the training sample set comprises training device parameter samples of training device samples and training environment parameter samples of an operating environment in which the training device samples are located;
and training the decision model according to the training equipment parameter sample and the training environment parameter sample so that the decision model can determine a decision scene according to the equipment parameter and the environment parameter.
In a third aspect, an embodiment of the present invention further provides an electronic device, including: memory, processor and computer program stored on the memory and executable on the processor, characterized in that the processor implements a device operating environment assessment method according to the first aspect or a decision model training method according to the second aspect when executing the computer program.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium storing computer-executable instructions, where the computer-executable instructions are configured to perform the apparatus operating environment assessment method according to the first aspect, or implement the decision model training method according to the second aspect.
The embodiment of the invention comprises the following steps: acquiring environmental parameters of an operating environment to be evaluated; acquiring equipment parameters and device parameters of the equipment sample to be evaluated in the running environment to be evaluated; determining a decision scene according to the environment parameters, the equipment parameters and a pre-trained decision model, and determining an equipment evaluation result of the equipment sample to be evaluated in the decision scene according to the device parameters of the equipment sample to be evaluated; and determining the operation environment evaluation result of the operation environment to be evaluated according to the equipment evaluation result. According to the scheme provided by the embodiment of the invention, the evaluation of the operating environment can be completed on the device in normal operation of the equipment, so that an information basis is provided for predicting the influence of the operating environment on the temperature of the equipment.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the example serve to explain the principles of the invention and not to limit the invention.
FIG. 1 is a flow chart of a method for evaluating an operating environment of a device according to an embodiment of the present invention;
fig. 2 is a flowchart of determining an apparatus evaluation result in an apparatus operating environment evaluation method according to another embodiment of the present invention;
fig. 3 is a flowchart of an apparatus evaluation result determined according to a device proportion in an apparatus operating environment evaluation method according to another embodiment of the present invention;
fig. 4 is a flowchart of determining an evaluation result of a device according to a risk level in a device operating environment evaluation method according to another embodiment of the present invention;
fig. 5 is a flowchart of determining an evaluation result of a device according to a risk level in a device operating environment evaluation method according to another embodiment of the present invention;
FIG. 6 is a flowchart of determining a decision scenario in a method for evaluating an operating environment of a device according to another embodiment of the present invention;
FIG. 7 is a flowchart of a decision model training method according to another embodiment of the present invention;
FIG. 8 is a flowchart of decision scenario determination in a decision model training method according to another embodiment of the present invention;
FIG. 9 is a flowchart of a method for training a decision model to generate a set of decision conditions according to another embodiment of the present invention;
FIG. 10 is a flow chart of preprocessing in a decision model training method according to another embodiment of the present invention;
FIG. 11 is a flow chart of determining a device temperature set in a decision model training method according to another embodiment of the present invention;
FIG. 12 is a data pre-processing flow diagram of an illustrative example of the principles of the invention;
FIG. 13 is a decision model training flow diagram of an illustrative implementation of the principles of the present invention;
FIG. 14 is a flowchart of an operating environment assessment method illustrative of the principles of the present invention;
fig. 15 is a schematic device diagram of an electronic apparatus according to another embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
It should be noted that although functional blocks are partitioned in a schematic diagram of an apparatus and a logical order is shown in a flowchart, in some cases, the steps shown or described may be performed in a different order than the partitioning of blocks in the apparatus or the order in the flowchart. The terms "first," "second," and the like in the description, in the claims, or in the drawings described above, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
The invention provides an equipment operating environment evaluation method, a judgment model training method and electronic equipment, wherein the equipment operating environment evaluation method comprises the following steps: obtaining environmental parameters of an operating environment to be evaluated; acquiring equipment parameters and device parameters of an equipment sample to be evaluated in an operating environment to be evaluated; determining a judgment scene according to the environment parameters, the equipment parameters and a pre-trained judgment model, and determining an equipment evaluation result of the equipment sample to be evaluated in the judgment scene according to the device parameters of the equipment sample to be evaluated; and determining the operation environment evaluation result of the operation environment to be evaluated according to the equipment evaluation result. According to the scheme provided by the embodiment of the invention, the evaluation of the operating environment can be completed on the device in normal operation of the equipment, so that an information basis is provided for predicting the influence of the operating environment on the temperature of the equipment.
The embodiments of the present invention will be further explained with reference to the drawings.
It should be noted that the device in the embodiment of the present invention may be various electronic devices and communication devices, and for convenience of description of the principle, a common Remote Radio Unit (RRU) is taken as an example device in the embodiment of the present invention, which does not limit the technical solution in the embodiment of the present invention.
As shown in fig. 1, fig. 1 is a method for evaluating an operating environment of a device according to an embodiment of the present invention, which includes, but is not limited to, step S110, step S120, step S130, and step S140.
Step S110, obtaining the environmental parameters of the running environment to be evaluated.
It should be noted that before obtaining the environmental parameters, the operating environment to be evaluated needs to be determined, where the operating environment to be evaluated may be any environment in which the risk of overheating of the device needs to be evaluated, such as an outdoor environment and a machine room for installing the RRU.
In an embodiment, the environmental parameter may be any type of parameter, such as air temperature and climate condition of outdoor environment, room temperature of indoor environment, and the like, and the environmental parameter related to heat dissipation of the device may be selected, which is not limited in this embodiment. It should be noted that, a person skilled in the art may adjust the obtaining manner of the environment parameter according to different operating environments to be evaluated, for example, the operating environment to be evaluated is an outdoor environment, and local temperature information may be obtained from the internet through location information of the environment and time information of the obtained data, and for example, the operating environment to be evaluated is an indoor environment, and temperature information may be obtained through a temperature measuring device disposed in the indoor environment, which is not described herein again.
Step S120, obtaining the device parameters and the device parameters of the device sample to be evaluated.
In an embodiment, before obtaining the device parameter and the device parameter, a device sample to be evaluated needs to be determined in an operating environment to be evaluated, where the device sample to be evaluated may be any device, such as a common RRU, the number of the device sample to be evaluated may be any, and the multiple determined device samples to be evaluated may be all devices of the same type, devices of the same type and different models, or devices of different types.
It should be noted that the device parameter may be any parameter related to the device heat generation amount, such as device power, a temperature value, memory occupation, and the like, and is selected according to an actual requirement, which is not limited in this embodiment.
In an embodiment, the device sample to be evaluated may be any device in the device sample to be evaluated, for example, when the device sample to be evaluated is an RRU, the device sample to be evaluated may be an optical module, a single board, a baseband, an intermediate frequency, a transceiver, a power amplifier, a power supply of the RRU, or another device capable of generating heat during an operation process, and this embodiment does not make too much limitation on a specific device type. It is understood that the device parameter may be a parameter related to heat generation during operation, such as a power value, an operating temperature value, and the like of the device, and a specific parameter type may be selected according to actual requirements.
It should be noted that, for the acquisition of device parameters, a specific device sample to be evaluated may be preset, and parameter acquisition may be performed in a targeted manner from the device sample to be evaluated, or after all parameters that can be acquired in the device sample to be evaluated are acquired, required parameters are extracted in a preprocessing manner, and a specific method may be adjusted according to actual conditions.
Step S130, determining a decision scene according to the environment parameters, the equipment parameters and the pre-trained decision model, and determining an equipment evaluation result of the equipment sample to be evaluated in the decision scene according to the device parameters of the equipment sample to be evaluated.
Based on the embodiment, the environmental parameters and the equipment parameters are parameters related to the equipment heat, the judgment scene is determined through the environmental parameters and the equipment parameters, the equipment sample to be evaluated can be limited in the known external conditions under the running environment to be evaluated, so that the fixed influence of the outside on the equipment heat is determined, and the prediction of the running environment to be evaluated is realized through the device parameters in the equipment sample to be evaluated; for example, the environmental parameter is air temperature, the equipment parameter is equipment power, the air temperature is determined by the climate condition, the power is determined according to the operation requirement, the heat influence of the two factors on the equipment can be determined, and under the determined air temperature and the determined power, the device parameter in the equipment sample to be evaluated determines the heating trend of the equipment sample to be evaluated, so that under the judgment scene, the prediction of the environment to be evaluated can be realized under the condition that the equipment is in normal operation according to the device parameter.
It is to be noted that the operation environment to be evaluated may be an operation environment in which the device is installed for the first time, or an operation environment in which a plurality of devices are already installed, and based on the above, a decision scenario may be determined according to the environment parameter and the device parameter of the environment to be evaluated, and then a device evaluation result of the device sample to be evaluated is obtained through the device parameter, so that the present embodiment does not excessively limit whether the device is installed for the first time in the operation environment.
In an embodiment, the device evaluation result may be in any embodiment form, and may be used to describe the overheating risk or trend of the device sample to be evaluated, for example, a plurality of risk levels may be divided, a higher risk level indicates that the device is more likely to be overheated, and a specific evaluation result form may be selected according to actual needs.
And step S140, determining an operation environment evaluation result of the operation environment to be evaluated according to the equipment evaluation result.
In one embodiment, during the evaluation of the operating environment to be evaluated, a plurality of samples of the device to be evaluated may be collected, and this embodiment does not detect the current temperature of the samples of the device to be evaluated, but estimates the overheating risk of the equipment sample to be evaluated in the running environment to be evaluated, in order to more accurately represent the evaluation result of the equipment heat change, the operating environment evaluation result of the operating environment to be evaluated may be determined by a second preset proportion, for example exceeding the second preset proportion, the device evaluation result is considered to be the operation environment evaluation result of the operation environment to be evaluated, or the second preset proportion is set to be a set of a plurality of proportion values, the specific operation environment evaluation result is determined according to the proportion value satisfied by the equipment evaluation result, the embodiment does not limit the specific manner, and the operation environment evaluation result can be determined by the equipment evaluation result.
In addition, referring to fig. 2, the device parameter includes a device temperature value of the device sample to be evaluated in the device sample to be evaluated, and step S130 in the embodiment shown in fig. 1 further includes, but is not limited to, the following steps:
step S210, determining a decision condition set corresponding to the device temperature value in a decision scene, wherein the decision condition set comprises a decision temperature condition and a risk level corresponding to the decision temperature condition;
step S220, determining the judgment temperature condition met by the device temperature value in the judgment condition set, and determining the risk grade corresponding to the met judgment temperature condition as the risk grade of the device sample to be evaluated;
step S230, determining an equipment evaluation result according to the device number of the device sample to be evaluated and the risk level of the device sample to be evaluated.
In an embodiment, the device parameter may include a device temperature value, the current temperature condition of the device sample to be evaluated can be more intuitively reflected by using the temperature value, the risk level can be determined in a quantitative numerical form in a decision scene, and other types of parameters may be used, which is not described herein again.
In an embodiment, the risk level may be a preset level for indicating the overheating risk, for example, "first level is easy to overheat", and the specific expression manner and the number of levels may be adjusted according to actual requirements, and may be used for expressing the overheating risk. It should be noted that, since the device parameter is a device temperature value, the decision temperature condition may be a temperature value used for distinguishing multiple risk levels, such as a threshold value a and a threshold value B, where a > B, when the device temperature value is greater than the threshold value a, the risk level of the device sample to be evaluated corresponding to the device temperature value is the highest level, and for example, the decision temperature condition may also be a temperature value interval C and a temperature value interval D, where values in the temperature value interval C and the temperature value interval D are not overlapped with each other, and a value in the temperature value interval C is greater than a value in the temperature value D, and when the device temperature value belongs to the temperature value interval D, the risk level of the corresponding device sample to be evaluated is the next highest level, and so on, which is not described herein again.
It should be noted that, in general, the heat generated by each device during operation is one of the components of the heat of the equipment, so the temperature of the device determines the heating condition of the equipment itself to some extent, and based on this, under the condition of the same equipment power and the same ambient temperature, the temperature value of the equipment can be estimated through the temperature value of the device, which is essentially the overheating risk of the equipment in the operating environment.
It should be noted that, because different devices have different heat resistance, the same temperature value has different overheating risks for different devices, for example, for some devices with poor heat resistance, even if the temperature value is low, there is a greater overheating risk, and therefore, the decision condition set needs to correspond to a specific device, and before determining the device sample to be evaluated, the decision condition set corresponding to the device sample needs to be determined. It is understood that the decision condition sets can also be set separately according to different specific devices, for example, refer to table 1 below.
TABLE 1 schematic diagram of decision condition sets for different devices
In addition, referring to fig. 3, the step S230 of the embodiment shown in fig. 2 further includes, but is not limited to, the following steps:
step S310, determining the device proportion, wherein the device proportion is the ratio of the number of the device samples to be evaluated with the same risk grade to the total number of the device samples to be evaluated;
and step S320, determining an equipment evaluation result according to the device proportion and the first preset proportion.
Based on the description of the above embodiment, the risk level is a preset risk level, and therefore, in the case of having a plurality of device samples to be evaluated, at least two device samples to be evaluated are likely to be determined as the same risk level, and according to the calculation of the device proportion, the device proportion of each risk level in the device samples to be evaluated can be determined, so as to determine the risk level of the device sample to be evaluated. It should be noted that, according to the above description, the number of the device ratios determined in the device sample to be evaluated is the same as the number of the determined risk levels, for example, if it is determined that the risk levels determined in the device sample to be evaluated include the highest level, the second highest level, and the low risk, the number of the device ratios that can be determined is three, and the three device ratios are respectively the highest device ratio, the second highest device ratio, and the low device ratio.
It should be noted that the risk level corresponding to the highest device occupation ratio may be directly used as the equipment evaluation result, and of course, since the risk level is used for describing the risk level of overheating, and in the actual evaluation process, a normal condition may also occur in the equipment sample to be evaluated, that is, the equipment sample to be evaluated has no risk of overheating in the operating environment to be evaluated, for example, the first preset ratio is set to 30%, it is determined that the risk level in the equipment sample to be evaluated includes the highest level, the second level, the low risk and no risk, the corresponding device occupation ratios are 20%, 10%, 20% and 50%, and at this time, the risk level satisfying the first preset ratio is no risk, and thus the equipment evaluation result may be determined to be no risk.
In addition, in one embodiment, at least one of:
at least two non-overlapping temperature value intervals;
and the temperature value sequences are arranged according to the numerical value order.
In an embodiment, the judgment temperature condition may be preset, or may be obtained by training and clustering through a neural network model, and a specific determination mode may be selected according to actual requirements. It is understood that the at least two temperature value intervals may be consecutive and non-overlapping intervals, such as [ a, B ] and [ B, C ], where a < B < C, and may also be numerically separated intervals, such as [ a, B ] and [ C, D ], where a < B < C < D, which is not limited in this embodiment. It can be understood that the temperature value sequence arranged according to the numerical value order may be a plurality of preset temperature values for determination, or may be a temperature value interval obtained in the above manner, and then the upper bound or the lower bound of the temperature value interval is taken as a threshold value, for example, the temperature value intervals determined in the above manner are [ a, B ] and [ C, D ], where a < B < C < D, and then a temperature value sequence may be formed by D and B, and when the device temperature value is greater than D, it is determined that the risk level is the highest level, and so on, and details are not repeated herein.
It is understood that, in addition to the above two manners, statistics of the temperature value interval may also be used as the decision temperature condition, for example, a median, an arithmetic mean, a variance, and the like of the temperature value interval.
In addition, referring to fig. 4, the step S310 of the embodiment shown in fig. 3 further includes, but is not limited to, the following steps:
step S410, sequentially comparing the device occupation ratio corresponding to each risk level with a first preset ratio according to the sequence of the risk levels from high to low;
step S420, when the device occupation ratio corresponding to the first comparison risk level is greater than a first preset ratio, determining the risk level used for comparison as the equipment evaluation result.
In one embodiment, in order to evaluate the risk of overheating of the equipment in the operating environment to be evaluated, after determining the risk level of each device sample to be evaluated in the equipment sample to be evaluated, the first preset ratio may be compared in order from high to low, and when the risk level is used to evaluate the overheating risk, the highest risk level that satisfies the condition may be selected, for example, with the first preset proportion set to 30%, the highest, second highest and lower levels are arranged from high to low according to the risk level, and the device ratios are determined to be 35%, 40% and 25%, since the highest-level device accounts for more than 35% > 30%, it represents that the equipment sample to be evaluated has satisfied the highest overheating risk level, and at this time, the risk level can be determined as the equipment evaluation result, and subsequent risk levels do not need to be determined, so that the obtained evaluation result can reflect the overheating risk of the equipment better.
It should be noted that the method for comparing the device occupation ratio of the risk level with the first preset ratio is only one optional method, and the method may also be used to compare the device occupation ratio with the first preset ratio with the largest value according to the actual requirement, and select a specific manner according to the actual requirement.
In addition, referring to fig. 5, the step S140 of the embodiment shown in fig. 1 further includes, but is not limited to, the following steps:
step S510, determining the equipment number of the equipment sample to be evaluated in the running environment to be evaluated;
step S520, determining the equipment ratio, wherein the equipment ratio is the ratio of the number of the equipment samples to be evaluated with the same equipment evaluation result to the total number of the equipment samples to be evaluated;
step S530, comparing the equipment occupation ratio with a second preset ratio according to the sequence from high to low of the risk level corresponding to the equipment evaluation result, and determining the equipment evaluation result corresponding to the equipment occupation ratio used for comparison as the operation environment evaluation result when the equipment occupation ratio is greater than the second preset ratio through the first comparison.
It should be noted that, in the running environment to be evaluated, if only one device sample to be evaluated is used to evaluate the overheating risk of the running environment to be evaluated, when the temperature of an internal device is high due to a failure of the device sample to be evaluated, it is likely that the obtained device evaluation result is an abnormal result due to the failure, and therefore, for accurate evaluation of the running environment to be evaluated, at least two device samples to be evaluated may be determined, and the influence of the device failure on the evaluation of the running environment to be evaluated is reduced in a device-to-device ratio manner.
In an embodiment, the device samples to be evaluated having the same device evaluation result are not limited to the same type of devices, and may also be a plurality of device samples to be evaluated having different device types, and the device evaluation results thereof may be the same.
In an embodiment, it should be noted that a manner of comparing that the ratio of the device is greater than the second preset ratio for the first time is similar to the comparison manner shown in fig. 4, and a person skilled in the art can obtain the comparison manner in step S530 in a similar manner, which is not described herein again.
Referring additionally to fig. 6, in one embodiment, the device parameters include a device power value, the ambient parameters include an ambient temperature value,
the step S130 of the embodiment shown in fig. 1 further includes, but is not limited to, the following steps:
step S610, inputting the equipment power value and the environment temperature value into a judgment model to obtain a judgment scene.
In an embodiment, the decision scenario may be a plurality of scenarios preset, and is determined by the device power value and the ambient temperature value, or may be determined by a decision model trained in advance. It can be understood that the decision model may be a model obtained by automatic learning through a machine learning method, and this embodiment does not improve a specific machine learning method, and only selects parameters for machine learning. For example, the device power value and the ambient temperature value are input to a trained decision model, and the decision model can output a determined decision scenario.
It should be noted that, determining a decision scenario by using the device power value and the environment temperature value can limit external factors affecting heat, so as to determine an overheating risk according to the device temperature in the device sample to be evaluated, for example, after determining the decision scenario, the device evaluation results determined by the device sample to be evaluated in the device sample to be evaluated are all high risks, and meet a second preset proportion, which means that the device has a high possibility of overheating in the operating environment to be evaluated, thereby implementing the evaluation of the operating environment in the normal operating process of the device.
In addition, as shown in fig. 7, fig. 7 is a decision model training method according to another embodiment of the present invention, which includes, but is not limited to, step S710 and step S720.
Step S710, determining a training sample set, where the training sample set includes training device parameter samples of training device samples and training environment parameter samples of an operating environment in which the training device samples are located.
It should be noted that the training sample set may be a plurality of training device samples collected in different operating environments, for example, data collection may be performed on a plurality of RRUs installed in different locations through a network management system, and for a decision model that performs automatic training by machine learning, the more the number of samples in the training sample set is, the more accurate the obtained decision model is, and a person skilled in the art has a motivation to select a specific number of samples according to actual situations.
And S720, training a decision model according to the training equipment parameter sample and the training environment parameter sample so that the decision model can determine a decision scene according to the equipment parameter and the environment parameter.
In an embodiment, the acquisition of the parameter samples of the training device may be implemented by acquiring an original log of the device, for example, for an RRU, the original log usually stores parameters of each internal device, information of a geographical location where the RRU is located, and time information acquired by each parameter, and data acquisition is performed through the original log, so that multiple parameters of the same device in different time periods can be quickly acquired, and compared with the case of acquiring data in real time, the efficiency of model training can be further improved. As will be understood by those skilled in the art, the generation of the original log may be to perform parameter acquisition for a period of time according to a set acquisition time granularity, for example, the acquisition time granularity of the RRU is set to 1 minute, the acquisition time is 3 days, and the RRU may acquire the temperature parameters of each device sample through a built-in temperature sensor every 1 minute, and store the temperature parameters as the original log by combining the time information and the location information. The power value of the training device sample may obtain the working power of the training device sample from the original log through the time information, and the specific obtaining method is not an improvement made in this embodiment and is not described herein again.
In an embodiment, the training environment parameter sample may be obtained through location information and time information, for example, for an RRU installed outdoors, an air temperature value of the area may be obtained from a network through the location information and the time information, and the air temperature value is used as the training environment parameter sample, or for an RRU installed in a machine room, the location information may be a machine room name, a temperature value corresponding to the time information may be determined through a management log of the machine room, the temperature value is used as the training environment parameter sample, and a specific type of the location information may be selected according to an actual requirement, which is not limited in this embodiment.
Referring additionally to fig. 8, in an embodiment, the training device parameter samples include power sample values of the training device samples, the training environment parameter samples include environmental temperature sample values of an operating environment where the training device samples are located, and the following steps are included but not limited to before step S720 of the embodiment shown in fig. 7 is executed:
step S810, determining a plurality of decision scenes according to the power sample value and the environment temperature sample value.
It is to be noted that, based on the description in the foregoing embodiment, in the training process of the decision model, a plurality of decision scenarios need to be determined in advance, so that when the operating environment to be evaluated is evaluated, the decision scenarios can be determined from the plurality of decision scenarios according to the input of the environment parameters and the device parameters, thereby implementing the pre-evaluation of the environment to be evaluated. It can be understood that the number of decision scenarios may be any, and it is sufficient to ensure that the training device parameter samples and the training environment parameter samples in each decision scenario are the same.
In addition, referring to fig. 9, in an embodiment, after performing step S810 of the embodiment shown in fig. 8, the following steps are further included, but not limited to:
step S910, in a decision scene, obtaining at least two decision temperature conditions according to a training device parameter sample and a preset rule;
step S920, determining a risk level corresponding to the decision temperature condition, and generating a decision condition set according to the decision temperature condition and the risk level.
It should be noted that, because the number of devices in the training sample set is large, the temperature condition may be obtained by dividing the temperature value interval for the temperature parameter used for training, or may be obtained by clustering data, and the specific manner is not limited in this embodiment. It can be understood that the number of risk levels may be determined according to the decision temperature condition, for example, if the decision temperature condition is a plurality of temperature value intervals, the risk levels only correspond to the temperature value intervals.
In addition, referring to fig. 10, in an embodiment, step S720 of the embodiment shown in fig. 7 further includes, but is not limited to, the following steps:
step S1010, carrying out data cleaning, filtering and quantization processing on the training equipment parameter sample;
step S1020, interpolation processing and quantification processing are carried out on the training environment parameter samples, so that the acquisition granularity of the training environment parameter samples is the same as that of the training equipment parameter samples;
and step S1030, associating the training equipment parameter samples and the training environment parameter samples with the same acquisition time.
In an embodiment, before training using data of the original log, data cleaning needs to be performed on the data in the original log, and a specific data cleaning manner is not an improvement made in this embodiment, and a common cleaning manner is adopted. It is understood that, as described in connection with the above embodiments, the original log is obtained by collecting data periodically, therefore, in order to obtain data samples for training, one sample may be set for each collection time, and the sample field may include: collecting time, equipment power value and device temperature value in the equipment, and adding other types of fields according to actual requirements, which is not described herein again; moreover, the data collected in the original log has a case of collection failure, so that all samples can be subjected to outlier cleaning, for example, if one or more field values of a certain sample are missing or invalid, the sample is discarded.
Based on the above embodiments, in order to eliminate interference caused by numerical fluctuation, filtering processing may be performed on the device power value and the device temperature value of the training sample set, for example, Savitzky-Golay filtering may be adopted, and the filtering parameters may be set as: the filter window length may be 5, the fitting polynomial order may be 3, and a specific numerical value may also be adjusted according to actual requirements or other filtering manners may be adopted, which is not limited in this embodiment.
In an embodiment, in the case of a large number of device samples, the obtained values are generally more dispersed, and the influence of similar values on the overheating risk of the device temperature is similar, for the convenience of training the decision model, the device power value and the device temperature value may be quantized, the values are divided into a plurality of value intervals, and an identification value of each value interval is determined, and the identification value is used as the value for training, for example, according to the following formula:
wherein, Power is Power, and size is Power quantization granularity, and takes 5W. It should be noted that the power quantization granularity may be adjusted according to a value range of the device power value and the device temperature value, which is not limited in this embodiment. It is understood that the identification value may be a statistical value such as an average value or a median value, and this embodiment is not limited in many ways.
In an embodiment, the principle and formula of the above embodiment may be referred to for quantization processing of the training environment parameter samples, and this embodiment is not described in detail. It should be noted that, when the location information is used to obtain the training environment parameter sample, the collection granularity of the collection granularity may be different from that of the device power value and the device temperature value, for example, the temperature value is used as the training environment parameter sample, and the temperature value may be updated once every hour, which is larger than the collection granularity of the device power value and the device temperature value, in this case, the correspondence of the values may be realized through interpolation processing, for example, adjacent temperature points are connected by a straight line in a coordinate system, and the corresponding temperature value is obtained from the coordinate system according to the collection granularity of the device power value and the device temperature value, or the correspondence of the data may be realized by other methods, which is not limited herein.
It should be noted that, after the correspondence between the training environment parameter sample, the device power value, and the device temperature value is realized based on the above embodiment, the data association may also be realized through the time information, so as to form sample data for training, where the associated sample field may include: and acquiring time, environment temperature value information, equipment power value and device temperature value.
In addition, referring to fig. 11, the training apparatus parameter sample further includes a device temperature value of the training device sample in the training apparatus sample, and before executing step S910 of the embodiment shown in fig. 9, further includes, but is not limited to, the following steps:
step S1110, determining a device temperature set, where the device temperature set is a set of all device temperature values of the same training device sample in a decision scene.
It should be noted that, because the overheating risks of different training device samples at the same temperature are not necessarily the same, the same training device sample can be formed into a device temperature set in a decision scene, and a plurality of decision temperature conditions are formed according to the temperature values in the device temperature set, so that the overheating risks of specific devices can be embodied more accurately.
In addition, in an embodiment, the preset rule includes at least one of the following:
clustering the device temperature values in the device temperature set to obtain at least two temperature value intervals, and setting the lower bound value of the temperature value intervals as a temperature judgment condition;
alternatively, the first and second electrodes may be,
determining at least two temperature value intervals from the device temperature set, and setting the determined temperature value intervals as temperature judgment conditions;
alternatively, the first and second electrodes may be,
and determining the temperature set of the device into at least two temperature value intervals, acquiring the statistical value of the temperature value intervals, and determining the statistical value as a temperature judgment condition.
In an embodiment, the clustering may adopt any existing clustering method, such as a maximum-minimum distance algorithm, a k-means clustering algorithm, a hierarchical clustering algorithm, and the like, and the following takes the maximum-minimum distance algorithm as an example, and a specific example is used for explaining the principle:
input device temperature set is { x1,x2,..,xNN is the number of the device temperature value in the device temperature setAn amount; determining the distance threshold factor theta to be 0.3, and determining the first clustering center to be Z1＝min(x1,x2,...,xN) Determining a device temperature distance calculation mode: dij＝|xi-xj|；
Calculating all device temperature values to Z1Distance D ofi1Wherein, i is 1,2,. N; computing
Then the second cluster center Z2＝xk；
Calculating all device temperature values to a clustering center Z1And Z2Distance D ofi1And Di2I ═ 1,2, ·, N; calculating Dl＝max{min(D11,D12),min(D21,D22),..,min(DN1,DN2) If Dl>θ·D12(wherein D12As a cluster center Z1And Z2Distance of) then the third cluster center Z3＝xlOtherwise, finishing the calculation of the clustering center;
calculating Dj＝max{min(D11,D12,D13),min(D21,D22,D23),..,min(DN1,DN2,DN3) If Dj>θ·D12Then the fourth clustering center Z4＝xjOtherwise, finishing the calculation of the clustering center;
and so on until the maximum and minimum distance is not more than theta.D12And then, finishing the calculation of the clustering center. After the calculation of the clustering centers is completed, all the device temperature values are divided into the categories to which the clustering centers closest to each other belong according to the nearest neighbor principle.
Based on the embodiment, a plurality of temperature value ranges of a certain training device sample in a decision scene are obtained according to a clustering method, and when the operating environment to be evaluated is evaluated, in order to facilitate comparison of device temperature values, a plurality of decision threshold values are determined according to each temperature value interval obtained from clustering, so that a decision threshold set of each training device sample is formed. It can be understood that the decision threshold value may be a lower bound value of each temperature value interval, and when the device temperature value is greater than the lower bound value, it represents that the device temperature value satisfies the threshold, for example, the clustering result of the device temperature set is { (min 1, max 1),., (min K, max K), (min J, max J) }, and all categories are arranged according to the ascending order of the temperature lower bound values, where min J and min K are lower bound values of the highest temperature category and the next highest temperature category of the device, respectively, and when the device temperature value is greater than min J, it may be determined that the device temperature value at least satisfies the risk level corresponding to the highest temperature category.
In an embodiment, the device temperature value in the device temperature set may be determined as at least two temperature value intervals according to an actual requirement standard, and when the device temperature value belongs to any one of the temperature value intervals, the device temperature value is determined to satisfy the judgment temperature condition. It can be understood that a statistical value may also be calculated by using a value of the temperature value interval through a statistical method, for example, an average value or a median value, and the obtained statistical value may be determined in the same manner as the decision threshold value in the above embodiment, and details are not described here again.
The following describes an exemplary embodiment of the present invention with a specific example in conjunction with fig. 12 to 14. It should be noted that, in this example, the RRU is taken as an example of the device, the environment parameter is taken as an example of the gas temperature value, the device parameter is taken as an example of the power, the temperature condition set is taken as an example of the decision threshold set, and the decision threshold value is taken as a device temperature value; meanwhile, for convenience of description, the risk levels in this example are "first-level excessive temperature prone", "second-level excessive temperature prone", and "normal", and are not described in detail later.
Referring to FIG. 10, data acquisition includes, but is not limited to, the following steps:
step S1210, external field data of the RRU are collected, wherein the external field data comprise collection time, equipment power and device temperature.
The specific data acquisition manner may refer to the description of the embodiment shown in fig. 7, and is not described herein again.
Step S1211, performing data cleaning, filtering and quantization on the external field data.
For a specific data cleaning, filtering and quantization processing manner, reference may be made to the description of the embodiment shown in fig. 8, and details are not repeated here.
In step S1220, the air temperature data is acquired, and interpolation processing and quantization processing are performed on the air temperature data.
For a specific interpolation processing and quantization processing manner, reference may be made to the description of the embodiment shown in fig. 8, and details are not repeated here.
Step S1230, the outfield data and the air temperature data are correlated.
For a specific association manner, reference may be made to the description of the embodiment shown in fig. 8, which is not described herein again.
Referring to fig. 13, decision model building includes, but is not limited to, the following steps:
in step S1310, a training sample set is generated.
The specific manner of generating the training sample set may refer to the description of the embodiment shown in fig. 7, and is not described herein again.
Step S1320, classify the samples in the sample set according to the decision scenario.
For a specific decision scene classification manner, reference may be made to the description of the embodiment shown in fig. 7, which is not described herein again.
Step S1330, clustering the device temperatures of all the decision scenes.
For a specific clustering manner, reference may be made to the above description about the embodiment of the preset rule, which is not described herein again.
Step S1340, generating a decision threshold set of all decision scenes.
The specific clustering manner of the decision threshold set may refer to the above description about the embodiment of the preset rule, and is not described herein again.
Referring to fig. 14, the detection of the excessive temperature of the equipment operating environment includes, but is not limited to, the following steps:
step S1420, obtaining a single RRU sample, determining a decision scene according to the power value of the RRU sample and the air temperature value of the operating environment, and determining a corresponding decision threshold set in the decision scene;
step S1430, comparing the device sample of the RRU sample with the decision threshold values of the decision threshold set, determining the device occupation ratio meeting each decision threshold value, executing step S1441 when the device occupation ratio meeting the highest threshold value is higher than a first preset ratio, executing step S1442 when the device occupation ratio meeting the highest threshold value is lower than the first preset ratio and the device occupation ratio meeting the second highest threshold value is higher than the first preset ratio, otherwise executing step S1443;
step S1441, marking the RRU sample as a first-stage over-temperature easily, and executing step S1450;
step S1442, marking the RRU sample as a secondary over-temperature easily, and executing step S1450;
step S1443, marking the RRU sample as normal, and executing step S1450;
step S1450, determining whether all the device samples of the RRU sample have been traversed, if not, continuing to perform step S1430, if yes, when the occupancy ratio of the first-stage equipment prone to over-temperature is higher than a second preset ratio, performing step S1451, when the occupancy ratio of the first-stage equipment prone to over-temperature is lower than the second preset ratio and the occupancy ratio of the second-stage equipment prone to over-temperature is higher than the second preset ratio, performing step S1452, otherwise, performing step S1453;
step S1451, marking the operation environment as a first-level easy over-temperature;
step S1452, marking the operation environment as a secondary easy over-temperature;
in step S1453, the operating environment is marked as normal.
In an embodiment, through the above steps, a decision scene can be determined according to the power value of the RRU sample and the air temperature value of the operating environment, the risk level of each device sample is determined according to the decision threshold set corresponding to the RRU sample in the decision scene, and the risk level of the RRU sample is further determined according to the risk level of the device sample, thereby completing the evaluation of the operating environment.
In addition, referring to fig. 15, an embodiment of the present invention also provides an electronic apparatus 1500, where the electronic apparatus 1500 includes: a memory 1510, a processor 1520, and a computer program stored on the memory 1510 and executable on the processor 1520.
The processor 1520 and the memory 1510 may be connected by a bus or other means.
Non-transitory software programs and instructions required to implement the device operating environment assessment method of the above-described embodiment are stored in the memory 1510, and when executed by the processor 1520, perform the device operating environment assessment method applied to the electronic device 1500 of the above-described embodiment, for example, perform the method steps S110 to S140 in fig. 1, the method steps S210 to S230 in fig. 2, the method steps S310 to S320 in fig. 3, the method steps S410 to S420 in fig. 4, the method steps S510 to S530 in fig. 5, the method step S610 in fig. 6 described above, or perform the decision model training method applied to the electronic device, for example, perform the method steps S710 to S720 in fig. 7, the method step S810 in fig. 8, the method steps S910 to S920 in fig. 9, the method steps S1010 to S1030 in fig. 10, and the method step S1110 in fig. 11 described above.
The above-described embodiments of the apparatus are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may also be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
Furthermore, an embodiment of the present invention also provides a computer-readable storage medium storing computer-executable instructions, which are executed by a processor or a controller, for example, by a processor in the above-mentioned embodiment of the electronic device, and can make the above-mentioned processor execute the device operating environment assessment method applied to the electronic device in the above-mentioned embodiment, for example, execute the above-mentioned method steps S110 to S140 in fig. 1, the method steps S210 to S230 in fig. 2, the method steps S310 to S320 in fig. 3, the method steps S410 to S420 in fig. 4, the method steps S510 to S530 in fig. 5, and the method step S610 in fig. 6, or execute the above-mentioned decision model training method applied to the electronic device, for example, execute the above-mentioned method steps S710 to S720 in fig. 7, the method step S810 in fig. 8, method steps S910 to S920 in fig. 9, method steps S1010 to S1030 in fig. 10, and method step S1110 in fig. 11. It will be understood by those of ordinary skill in the art that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, or suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
While the preferred embodiments of the present invention have been described in detail, it will be understood by those skilled in the art that the foregoing and various other changes, omissions and deviations in the form and detail thereof may be made without departing from the scope of this invention.
Claims (15)
1. An equipment operating environment assessment method comprises the following steps:
acquiring environmental parameters of an operating environment to be evaluated;
acquiring equipment parameters and device parameters of the equipment sample to be evaluated in the running environment to be evaluated;
determining a decision scene according to the environment parameters, the equipment parameters and a pre-trained decision model, and determining an equipment evaluation result of the equipment sample to be evaluated in the decision scene according to the device parameters of the equipment sample to be evaluated;
and determining the operation environment evaluation result of the operation environment to be evaluated according to the equipment evaluation result.
2. The method according to claim 1, wherein the device parameters include a device temperature value of a device sample to be evaluated in the device sample to be evaluated, and the determining, according to the device parameters of the device sample to be evaluated, an apparatus evaluation result of the device sample to be evaluated in the decision scenario includes:
determining a decision condition set corresponding to the device temperature value in the decision scene, wherein the decision condition set comprises a decision temperature condition and a risk level corresponding to the decision temperature condition;
determining a judgment temperature condition met by the device temperature value in the judgment condition set, and determining a risk grade corresponding to the met judgment temperature condition as a risk grade of the device sample to be evaluated;
and determining the equipment evaluation result according to the device number of the device sample to be evaluated and the risk level of the device sample to be evaluated.
3. The method of claim 2, wherein determining the equipment assessment result according to the device number of the device sample to be assessed and the risk level of the device sample to be assessed comprises:
determining a device ratio which is the ratio of the number of the device samples to be evaluated with the same risk level to the total number of the device samples to be evaluated;
and determining the equipment evaluation result according to the device proportion and a first preset proportion.
4. The method of claim 2, wherein the decision temperature condition comprises at least one of:
at least two non-overlapping temperature value intervals;
the temperature value sequences are arranged according to the numerical value sequence.
5. The method of claim 2, wherein determining the device evaluation result according to the device fraction and a first preset ratio comprises:
sequentially comparing the device occupation ratio corresponding to each risk level with the first preset ratio according to the sequence of the risk levels from high to low;
and when the device occupation ratio corresponding to the first comparison risk level is larger than the first preset ratio, determining the risk level used for comparison as the equipment evaluation result.
6. The method according to claim 5, wherein the determining an evaluation result of the operating environment to be evaluated according to the equipment evaluation result comprises:
determining the equipment number of the equipment samples to be evaluated in the running environment to be evaluated;
determining the equipment proportion which is the ratio of the number of the equipment samples to be evaluated with the same equipment evaluation result to the total number of the equipment samples to be evaluated;
and comparing the equipment occupation ratio with a second preset ratio according to the sequence from high to low of the risk level corresponding to the equipment evaluation result, and determining the equipment evaluation result corresponding to the equipment occupation ratio used for comparison as the operating environment evaluation result when the equipment occupation ratio is greater than the second preset ratio through the first comparison.
7. The method of claim 1, wherein the device parameter comprises a device power value, wherein the environment parameter comprises an environment temperature value, and wherein determining a decision scenario according to the environment parameter, the device parameter, and a pre-trained decision model comprises:
and inputting the equipment power value and the environment temperature value into the judgment model to obtain the judgment scene.
8. A decision model training method, comprising:
determining a training sample set, wherein the training sample set comprises training device parameter samples of training device samples and training environment parameter samples of an operating environment in which the training device samples are located;
and training the decision model according to the training equipment parameter sample and the training environment parameter sample so that the decision model can determine a decision scene according to the equipment parameter and the environment parameter.
9. The method of claim 8, wherein the training device parameter samples comprise power sample values of the training device samples, wherein the training environment parameter samples comprise ambient temperature sample values of an operating environment in which the training device samples are located, and wherein prior to the training of the decision model based on the training device parameter samples and the training environment parameter samples, comprising:
and determining a plurality of decision scenes according to the power sample value and the environment temperature sample value.
10. The method of claim 9, after determining a number of decision scenarios from the power sample value and the ambient temperature sample value, further comprising:
in the judgment scene, obtaining at least two judgment temperature conditions according to the training equipment parameter sample and a preset rule;
and determining a risk level corresponding to the judgment temperature condition, and generating a judgment condition set according to the judgment temperature condition and the risk level.
11. The method of claim 8, wherein after obtaining the training device parameter samples of the training device samples and the training environment parameter samples of the environment in which the training device samples are located, further comprising:
carrying out data cleaning, filtering and quantification processing on the training equipment parameter sample;
performing interpolation processing and quantization processing on the training environment parameter samples to enable the acquisition granularity of the training environment parameter samples to be the same as that of the training equipment parameter samples;
and associating the training equipment parameter sample and the training environment parameter sample with the same acquisition time.
12. The method of claim 10, wherein the training device parameter samples further include device temperature values of training device samples in the training device samples, and further comprising, before the deriving at least two decision temperature conditions according to the training device parameter samples and preset rules:
and determining a device temperature set, wherein the device temperature set is a set of all device temperature values of the same training device sample in the judgment scene.
13. The method of claim 12, wherein the preset rules comprise at least one of:
clustering the device temperature values in the device temperature set to obtain at least two temperature value intervals, and setting a lower bound value of the temperature value intervals as the judgment temperature condition;
alternatively, the first and second electrodes may be,
determining at least two temperature value intervals from the device temperature set, and setting the determined temperature value intervals as the judgment temperature conditions;
alternatively, the first and second electrodes may be,
and determining the device temperature set into at least two temperature value intervals, acquiring the statistic value of the temperature value intervals, and determining the statistic value as the judgment temperature condition.
14. An electronic device, comprising: memory, processor and computer program stored on the memory and executable on the processor, characterized in that the processor implements a device operating environment assessment method according to any one of claims 1 to 7 or a decision model training method according to any one of claims 8 to 13 when executing the computer program.
15. A computer-readable storage medium storing computer-executable instructions for performing the device operating environment assessment method of any one of claims 1 to 7, or implementing the decision model training method of any one of claims 8 to 13.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011406910.1A CN114610559A (en) | 2020-12-04 | 2020-12-04 | Equipment operation environment evaluation method, judgment model training method and electronic equipment |
| PCT/CN2021/124160 WO2022116710A1 (en) | 2020-12-04 | 2021-10-15 | Device running environment evaluation method, decision model training method, and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011406910.1A CN114610559A (en) | 2020-12-04 | 2020-12-04 | Equipment operation environment evaluation method, judgment model training method and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114610559A true CN114610559A (en) | 2022-06-10 |
Family
ID=81852906
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011406910.1A Pending CN114610559A (en) | 2020-12-04 | 2020-12-04 | Equipment operation environment evaluation method, judgment model training method and electronic equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114610559A (en) |
| WO (1) | WO2022116710A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116431458A (en) * | 2023-06-08 | 2023-07-14 | 深圳市华卓智能科技有限公司 | Intelligent management system and method for tablet personal computer |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114997726B (en) * | 2022-06-30 | 2024-04-09 | 精效悬浮(苏州)科技有限公司 | Stability performance evaluation method and system for nitrogen blower |
| CN116629726B (en) * | 2023-05-31 | 2023-11-17 | 常州润来科技有限公司 | Environment monitoring management method and system for precise copper pipe packaging workshop |
| CN117032415B (en) * | 2023-06-29 | 2024-01-30 | 兴容(上海)信息技术股份有限公司 | Equipment data supervision system and method based on temperature change |
| CN116975567B (en) * | 2023-07-28 | 2024-03-15 | 上海优立检测技术股份有限公司 | Method, system, equipment and storage medium for testing radiation interference resistance of server |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8266078B2 (en) * | 2009-02-06 | 2012-09-11 | Microsoft Corporation | Platform for learning based recognition research |
| CN103326352B (en) * | 2013-05-21 | 2015-12-09 | 国家电网公司 | A kind of power distribution network cable line local overheating Risk Identification |
| CN110175386B (en) * | 2019-05-21 | 2022-11-25 | 陕西科技大学 | Method for predicting temperature of electrical equipment of transformer substation |
| CN111026790A (en) * | 2019-12-09 | 2020-04-17 | 上海勘察设计研究院(集团)有限公司 | Structure safety assessment and forecasting method based on data mining |
-
2020
- 2020-12-04 CN CN202011406910.1A patent/CN114610559A/en active Pending
-
2021
- 2021-10-15 WO PCT/CN2021/124160 patent/WO2022116710A1/en active Application Filing
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116431458A (en) * | 2023-06-08 | 2023-07-14 | 深圳市华卓智能科技有限公司 | Intelligent management system and method for tablet personal computer |
| CN116431458B (en) * | 2023-06-08 | 2024-05-31 | 深圳市聚人科技有限公司 | Intelligent management system and method for tablet personal computer |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022116710A1 (en) | 2022-06-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114610559A (en) | Equipment operation environment evaluation method, judgment model training method and electronic equipment | |
| US20160217378A1 (en) | Identifying anomalous behavior of a monitored entity | |
| KR102215690B1 (en) | Method and apparatus for time series data monitoring | |
| WO2019196869A1 (en) | Method for determining list of patrolling base stations, and patrolling apparatus | |
| CN111176953B (en) | Abnormality detection and model training method, computer equipment and storage medium | |
| CN113868953B (en) | Multi-unit operation optimization method, device and system in industrial system and storage medium | |
| CN117078048B (en) | Digital twinning-based intelligent city resource management method and system | |
| CN103577662A (en) | Method and device for determining electricity consumption condition or environmental condition of household electrical appliances | |
| CN111046968A (en) | Road network track clustering analysis method based on improved DPC algorithm | |
| CN111078512A (en) | Alarm record generation method and device, alarm equipment and storage medium | |
| US20140088945A1 (en) | System and method for an energy management system | |
| CN117093461A (en) | Method, system, equipment and storage medium for time delay detection and analysis | |
| CN113094448B (en) | Analysis method and analysis device for residence empty state and electronic equipment | |
| CN110597792A (en) | Multistage redundant data fusion method and device based on synchronous line loss data fusion | |
| CN114338351A (en) | Network abnormal root cause determination method and device, computer equipment and storage medium | |
| CN117118810B (en) | Network communication abnormity early warning method and system | |
| CN116562746B (en) | Bedding and clothing data monitoring method and related device of bedding and clothing logistics site | |
| US9172552B2 (en) | Managing an entity using a state machine abstract | |
| US20230034061A1 (en) | Method for managing proper operation of base station and system applying the method | |
| CN110770753B (en) | Device and method for real-time analysis of high-dimensional data | |
| JP6625839B2 (en) | Load actual data determination device, load prediction device, actual load data determination method, and load prediction method | |
| CN116365519A (en) | Power load prediction method, system, storage medium and equipment | |
| CN114429240A (en) | Method and device for monitoring running state of highway equipment | |
| US20150347213A1 (en) | Apparatus and method for system monitoring | |
| CN110569277A (en) | Method and system for automatically identifying and classifying configuration data information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20220610 |